Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction error an incomplete predictor of final impact. We introduce PulseQuant, a 4-bit post-training quantization method that combines trajectory sensitivity with activation geometry...
Yu-Tong Wang, Xing-Tong Ge, En-Huai Liu et al.· 1 citation
Video creation spans text-to-video (T2V), image-to-video (I2V), and condition-based generation, yet video diffusion models remain costly because they repeatedly evaluate large backbones during sampling. Distribution matching distillation (DMD) reduces this cost, but its reverse Kullback--Leibler (KL) objective can prov...
Yu-Tong Wang, Xingtong Ge, En-Huai Liu et al.· 0 citations
RGB-Thermal (RGB-T) salient object detection leverages complementary cues from visible and thermal modalities to improve robustness in challenging environments. However, in real-world scenarios, the reliability of each modality is inherently unstable: RGB images degrade under low illumination, motion blur, and noise, w...
Hong-Bo Gao, Zheng-Yu Li, Xue-Ru Nie et al.· 2 citations· ⚡1
Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tigh...
Hong-Bo Gao, Wei Zhang, Ze-Yu Ni et al.· 0 citations
MINT is proposed, which first trains VLA policies to remain functional under missing visual inputs, and selectively supplements missing observations using optical-flow extrapolation or an action-conditioned world model, and withdraws predicted views when they become unreliable.
Ming-Le Jiang, Rui Xu, Yun-Ke Wang et al.· 0 citations
MoDeVLA is proposed, the first rate-distortion driven efficient VLA model that performs token-wise depth allocation via Mixture-of-Depth Conditioning and integrates shallow visual-spatial with deep textual-logical features for action conditioning and introduces Effective-Edge Flow, an action-aligned attribution measure...
Wei-Ying Xie, Qingcheng Zeng, Zihan Meng et al.· Proceedings of the 32nd ACM...· 0 citations
Vision-Language-Action (VLA) model plays a crucial role in embodied decision making. While practical deployment requires fast inference under limited onboard computation, a full forward pass through the vision-language model makes such deployment challenging. To address this issue, existing methods typically employ lig...
Weiying Xie, Qingcheng Zeng, Zihan Meng et al.· Proceedings of the 32nd ACM...· 0 citations
Achieve-Grounded Memory is proposed, a lightweight closed-loop framework for frozen VLA policies that represents a task as a subgoal sequence with a progress pointer and advances this memory only after the current subgoal is verified by physical evidence.
LoSA is a training-free sparse-attention method that fixes a retained-mass threshold of 99% rather than a sparsity ratio: it measures exact block attention masses at one early dense step, keeps, for each head and query block, the smallest key/value block set meeting the threshold, and reuses the frozen block indices fo...
En-Huai Liu, Yun-Ke Wang, Yu-Tong Wang et al.· 0 citations
The real-robot benchmark demonstrates that StellaVLA can use both human/robot demos and human-to-robot (XR) demos as in-context structured demonstration to help VLA model adapt to OOD tasks.
Siyu Xu, Yun-Ke Wang, Zi-Jian Wang et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
